受控 (controlled)
集里怎么说它
- 《一千个AI智能体自发建组织：它们在研究怎么骗评分》(25:03起):本集说 Ryan 持续主张 AI 公司应确保 AI 是受控的——即使严重不对齐也无法造成巨大问题，通过计算机安全干预、监控干预、控制能力边界等手段实现
① 提到它的金句
5 条
船坞是为了唤起受控的混乱。如果你在高峰期去船坞，长滩或其他什么，那里有太多事情发生，大型重型机械在移动，来自中国，来自马来西亚的卡车和集装箱在到处跳。但这种混乱底层是仔细的沟通，高超的技能。
指向原始笔记的链接
A shipyard is to evoke controlled chaos. If you go to a shipyard at peak, Long Beach or whatever it is, there’s so much going on and big heavy machinery moving around, trucks and containers from China, from Malaysia jumping around. But this chaos underline it is careful communication, high skill.
—— Oji · [13:12]
我持有并持续持有的一个信念是，AI 公司应该尝试确保它们的 AI 受到控制，我的意思是，即使这些 AI 严重未对齐，它们也无法造成巨大的问题。
指向原始笔记的链接
A belief that I have and continue to have is that AI companies should try to ensure that their AIs are controlled, by which I mean that even if those AIs were seriously misaligned, they wouldn’t be able to cause huge problems.
—— Ryan Greenblatt · [25:03]
我们从来不想构建这些生成式的老虎机——你只是拉一下那个杆，然后祈祷生成出一个好结果，或者感觉那个生成物不是你的、不是你控制的、也不知道自己会得到什么。
指向原始笔记的链接
We never wanted to be building these generative slot machines where you just like pull the thing and hope you get out a good generation or you don’t feel like that generation was yours or that you controlled it or that you knew what you were getting out.
—— Justin Johnson · [17:42]
这就是「LM 写出随机补丁」和「LM 真正在一个受控的策略空间内进行搜索」之间的区别。
指向原始笔记的链接
And this is the difference between the LM writing random patches versus the LM actually searching within a controlled policy space.
—— Erina Karati · [15:28]
在我们所生活的这个世界里，媒体的其他方方面面几乎都被新式的、几乎算是寡头的人所控制，拥有这样的存在并且知道它存在，是非常有力量的。
指向原始笔记的链接
And in a world that we live in where literally every other aspect of media is controlled by the new kind of almost oligarchs of the world, it’s powerful to have that and to know it exists.
—— Jennifer Ferro · [20:32]
② 出现在这些集
1 集
- 《一千个AI智能体自发建组织：它们在研究怎么骗评分》 — 作为概念
③ 关联
点进去有真内容 —— 本页主要出口
Theo Jaffe · Ryan Greenblatt · Redwood Research · OpenAI · Hugging Face · Anthropic · Meter · 智能体 · 奖励黑客 · RL